© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13934
    Prev
    Next
    INDEX
    Explanations

    vegetarian protein sources such as beans, legumes, peas, and soybeans

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    555
    +0.19
    0.9%
    32
    +0.18
    0.8%
    1145
    +0.18
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.19
    0.02
    395
    +0.18
    0.03
    1983
    +0.18
    0.02
    Negative Logits
     Horowitz
    -0.60
     thuy
    -0.57
     McCra
    -0.55
     Hiller
    -0.54
     totalPrice
    -0.51
     Bartholo
    -0.51
    Allister
    -0.51
     Loth
    -0.50
     perry
    -0.50
     Bartolo
    -0.48
    POSITIVE LOGITS
     bean
    1.52
     beans
    1.51
     Bean
    1.44
    bean
    1.42
     Beans
    1.38
    Bean
    1.33
    beans
    1.25
    Beans
    1.25
    BEAN
    1.15
    getBean
    0.83
    Activations Density 0.168%

    No Known Activations